News Comments:Exploring, Modeling, and Online Prediction

  • Manos Tsagkias
  • Wouter Weerkamp
  • Maarten de Rijke
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5993)

Abstract

Online news agents provide commenting facilities for their readers to express their opinions or sentiments with regards to news stories. The number of user supplied comments on a news article may be indicative of its importance, interestingness, or impact. We explore the news comments space, and compare the log-normal and the negative binomial distributions for modeling comments from various news agents. These estimated models can be used to normalize raw comment counts and enable comparison across different news sites. We also examine the feasibility of online prediction of the number of comments, based on the volume observed shortly after publication. We report on solid performance for predicting news comment volume in the long run, after short observation. This prediction can be useful for identifying news stories with the potential to “take off,” and can be used to support front page optimization for news sites.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Altheide, D.L.: Qualitative Media Analysis (Qualitative Research Methods). Sage Pubn. Inc., Thousand Oaks (1996)Google Scholar
  2. 2.
    Chung, D.S.: Interactive features of online newspapers: Identifying patterns and predicting use of engaged readers. J. Computer-Mediated Communication 13(3), 658–679 (2008)CrossRefGoogle Scholar
  3. 3.
    De Choudhury, M., Sundaram, H., John, A., Seligmann, D.D.: What makes conversations interesting? In: WWW 2009, April 2009, p. 331 (2009)Google Scholar
  4. 4.
    Duarte, F., Mattos, B., Bestravras, A., Almedia, V., Almedia, J.: Traffic characteristics and communication patterns in blogosphere. In: ICWSM 2006 (March 2007)Google Scholar
  5. 5.
    Kaltenbrunner, A., Gomez, V., Lopez, V.: Description and prediction of slashdot activity. In: LA-WEB 2007, pp. 57–66 (2007)Google Scholar
  6. 6.
    Kaltenbrunner, A., Gómez, V., Moghnieh, A., Meza, R., Blat, J., López, V.: Homogeneous temporal activity patterns in a large online communication space. CoRR (2007)Google Scholar
  7. 7.
    Lee, J.G., Salamatian, K.: Understanding the characteristics of online commenting. In: CONEXT 2008, pp. 1–2 (2008)Google Scholar
  8. 8.
    Mishne, G., de Rijke, M.: Capturing global mood levels using blog posts. In: AAAICAAW, pp. 145–152 (2006)Google Scholar
  9. 9.
    Mishne, G., de Rijke, M.: A study of blog search. In: Lalmas, M., MacFarlane, A., Rüger, S.M., Tombros, A., Tsikrika, T., Yavlinsky, A. (eds.) ECIR 2006. LNCS, vol. 3936, pp. 289–301. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  10. 10.
    Mishne, G., Glance, N.: Leave a reply: An analysis of weblog comments. In: Third annual workshop on the Weblogging ecosystem (2006)Google Scholar
  11. 11.
    Ogilvie, P.: Modeling blog post comment counts (July 2008), http://livewebir.com/blog/2008/07/modeling-blog-post-comment-counts/
  12. 12.
    Schuth, A., Marx, M., de Rijke, M.: Extracting the discussion structure in comments on news-articles. In: WIDM 2007, pp. 97–104 (2007)Google Scholar
  13. 13.
    Sheskin, D.J.: Handbook of Parametric and Nonparametric Statistical Procedures. Chapman & Hall/CRC, USA (2000)MATHGoogle Scholar
  14. 14.
    Szabó, G., Huberman, B.A.: Predicting the popularity of online content. CoRR, abs/0811.0405 (2008)Google Scholar
  15. 15.
    Tsagkias, M., Weerkamp, W., de Rijke, M.: Predicting the Volume of Comments on Online News Stories. In: CIKM 2009, pp. 1765–1768 (2009)Google Scholar
  16. 16.
    Wu, F., Huberman, B.A.: Novelty and collective attention pnas, http://www.pnas.org/content/104/45/17599.abstract

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Manos Tsagkias
    • 1
  • Wouter Weerkamp
    • 1
  • Maarten de Rijke
    • 1
  1. 1.ISLAUniversity of AmsterdamAmsterdamThe Netherlands

Personalised recommendations